Yi-Chen (Howard) Lo

Hi guys, I just released the ["CVPR 2020 Notes" on my Medium blog](https://medium.com/@howardyclo/cvpr-2020-notes-9b3bbd357b2d). Please check it out!

### Metadata - Speaker: Cedric Archambeau - Video: https://www.youtube.com/watch?v=pB1LmZWK_N8 - Website (more about HPO and NAS): https://hangzhang.org/CVPR2020/ - See more on my NAS survey: #55 ### Hyper-parameter Tuning as Global...

## Neural Architecture Search TL;DR This TL;DR aims to help myself getting a quick view of neural architecture search literature. Hopes it helps you too 😁! > Designing neural network...

### Update Date: 2020.04.18 - [A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning](http://openaccess.thecvf.com/content_cvpr_2017/papers/Yim_A_Gift_From_CVPR_2017_paper.pdf). Yim et al. KAIST. CVPR 2017. - [Similarity-Preserving Knowledge Distillation](http://openaccess.thecvf.com/content_ICCV_2019/papers/Tung_Similarity-Preserving_Knowledge_Distillation_ICCV_2019_paper.pdf). Tung et al....

## Last Update Date: 2020/03/22 ### Tutorials and Seminars - [Andrew Gordon Wilson on Bayesian deep learning; Primer: Pavel Izmailov and Polina Kirichenko](https://www.youtube.com/watch?v=GXs9Pmp6IKQ). Broad Institute of MIT and Harvard. [[Slides](https://polkirichenko.github.io/MIA_talk.pdf)]....

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

1

### Metadata - Authors: Yarin Gal & Zoubin Ghahramani - Organization: University of Cambridge - Conference: ICML 2016 - Paper: https://arxiv.org/pdf/1506.02142.pdf - Appendix: https://arxiv.org/pdf/1506.02157.pdf (In-depth review of dropout, Gaussian processes...

Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates

1

### Metadata - Author: Leslie N. Smith & Nicholay Topin - Organization: U.S. Naval Research Laboratory & University of Maryland - Paper: https://arxiv.org/pdf/1708.07120.pdf - Code: https://github.com/lnsmith54/super-convergence (Caffe) > Although this...

### Hello Guys Just publish my first blogpost on Medium — [*"NeurIPS 2019 Notes"*](https://medium.com/@howardyclo/neurips-2019-notes-83fb8d15b5e3). I highlight some of interesting research that I noticed at the conference. Here are the table...

Cold Fusion: Training Seq2Seq Models Together with Language Models

6

### Metadata - Authors: Anuroop Sriram, Heewoo Jun, Sanjeev Satheesh and Adam Coates - Organization: Baidu Research, Sunnyvale, CA, USA. - Release Date: 2017 on Arxiv - Link: https://arxiv.org/pdf/1708.06426.pdf

Selfie: Self-supervised Pretraining for Image Embedding

1

### Metadata - Authors: Trieu H. Trinh, Minh-Thang Luong, Quoc V. Le - Organization: Google Brain - Paper: https://arxiv.org/abs/1906.02940